mlsanityData to 14 Oct 2026

A2-DIDM: Privacy-preserving Accumulator-enabled Auditing for Distributed Identity of DNN Model

arXiv 2405.04108 ↗First posted 7 May 2024cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent booming development of Generative Artificial Intelligence (GenAI) has facilitated model commercialization to reinforce the model performance, including licensing or trading Deep Neural Network (DNN) models. However, DNN model trading may violate the benefit of the model owner due to unauthorized replications or misuse of the model. Model identity auditing is a challenging issue in protecting DNN model ownership, and verifying the integrity and ownership of models is one of the critical obstacles. In this paper, we focus on the above issue and propose an underlineAccumulator-enabled underlineAuditing for underlineDecentralized underlineIdentity of DNN underlineModel (A2-DIDM) that utilizes blockchain and zero-knowledge techniques to protect data and function privacy while ensuring the lightweight on-chain ownership verification. The proposed model presents a scheme of identity records via configuring model weight checkpoints with zero-knowledge proofs, which incorporates predicates to capture incremental state changes in model weight checkpoints. Our scheme ensures both computational integrity and programmability in DNN training process so that the uniqueness of the weight checkpoint sequence in a DNN model is preserved. %to ensure the correctness of model identity auditing, so that the uniqueness of the weight checkpoint sequence in a DNN model is preserved. A2-DIDM also addresses privacy protections in decentralized identity. We systematically analyze the security and robustness of our proposed model and further evaluate the effectiveness and usability of auditing DNN model identities. The code is available at https://github.com/xtx123456/A2-DIDM.git.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 59 references that are in the map. First posted on arXiv 7 May 2024.

Builds on

26 of 59 references.

References · 26

  1. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  2. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 201
  3. 2020Entangled Watermarks as a Defense against Model Extractioncited by 149
  4. 2022ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyondcited by 117
  5. 2021Dataset Inference: Ownership Resolution in Machine Learningcited by 116
  6. 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 100
  7. 2023Protecting Language Generation Models via Invisible Watermarkingcited by 90
  8. 2021Proof-of-Learning: Definitions and Practicecited by 84
  9. 2019How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNNcited by 66
  10. 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 61
  11. 2020Model Watermarking for Image Processing Networkscited by 56
  12. 2019Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processescited by 53
14 more
  1. 2021Defending against Model Stealing via Verifying Embedded External Featurescited by 46
  2. 2022SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoderscited by 45
  3. 2022Dataset Inference for Self-Supervised Modelscited by 36
  4. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  5. 2022On the Difficulty of Defending Self-Supervised Learning against Model Extractioncited by 22
  6. 2023Tools for Verifying Neural Models' Training Datacited by 22
  7. 2022Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networkscited by 21
  8. 2021"Adversarial Examples" for Proof-of-Learningcited by 20
  9. 2022Proof-of-Learning is Currently More Broken Than You Thinkcited by 12
  10. 2023martFL: Enabling Utility-Driven Data Marketplace with a Robust and Verifiable Federated Learning Architecturecited by 11
  11. 2021SoK: Machine Learning Governancecited by 10
  12. 2023FedRight: An Effective Model Copyright Protection for Federated Learningcited by 8
  13. 2022Robust and Large-Payload DNN Watermarking via Fixed, Distribution-Optimized, Weightscited by 5
  14. 2023On Function-Coupled Watermarks for Deep Neural Networkscited by 1

Built on by

Not cited yet.